Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ pnpm build # production build (agent + web)
LLM_PROVIDER=cliproxy
LLM_BASE_URL=http://localhost:8317/v1
LLM_API_KEY=dummy-key
LLM_MODEL=gpt-4o # 또는 claude-3-5-sonnet, gemini-2.0-flash
LLM_MODEL=gpt-5.5(xhigh) # CLIProxyAPI thinking suffix: GPT-5.5 + xhigh reasoning
```

**Trade-off**: 로컬 라우터 별도 실행 필요. 캐시·모델 비교에 유리.
Expand Down
4 changes: 2 additions & 2 deletions packages/agent/.env.example
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ LLM_PROVIDER=cliproxy
# (옵션 1) CLIProxyAPI 로컬 라우터 — Claude/GPT/Gemini 통합 (https://github.com/router-for-me/CLIProxyAPI)
CLIPROXY_BASE_URL=http://localhost:8317/v1
CLIPROXY_API_KEY=dummy-key
CLIPROXY_MODEL=gpt-4o
CLIPROXY_MODEL=gpt-5.5(xhigh)

# (옵션 2) OpenAI 직접 — 비용/속도 안정. LLM_PROVIDER=openai 와 함께.
# OPENAI_API_KEY=sk-...
Expand All @@ -28,4 +28,4 @@ CLIPROXY_MODEL=gpt-4o
# Canonical aliases — 위 3가지 옵션 중 어느 것도 매핑되지 않으면 이 3개로 직접 지정 가능
LLM_BASE_URL=http://localhost:8317/v1
LLM_API_KEY=dummy-key
LLM_MODEL=gpt-4o
LLM_MODEL=gpt-5.5(xhigh)
12 changes: 6 additions & 6 deletions packages/agent/src/config/models.ts
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
/** Default model assignments per agent role. Each prompt frontmatter (D-8) overrides per-call. */

export const DEFAULT_MODELS = {
intent: "gpt-4o-mini",
generator: "gpt-4o",
constraintCritic: "gpt-4o-mini",
refiner: "gpt-4o",
solver: "gpt-4o",
objectiveLlm: "gpt-4o-mini",
intent: "gpt-5.5(xhigh)",
generator: "gpt-5.5(xhigh)",

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2: Default model IDs now use a provider-specific alias format (gpt-5.5(xhigh)) that is passed unchanged to OpenAI, which expects the base model slug and separate reasoning-effort options.

Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At packages/agent/src/config/models.ts, line 5:

<comment>Default model IDs now use a provider-specific alias format (`gpt-5.5(xhigh)`) that is passed unchanged to OpenAI, which expects the base model slug and separate reasoning-effort options.</comment>

<file context>
@@ -1,12 +1,12 @@
-  solver: "gpt-4o",
-  objectiveLlm: "gpt-4o-mini",
+  intent: "gpt-5.5(xhigh)",
+  generator: "gpt-5.5(xhigh)",
+  constraintCritic: "gpt-5.5(xhigh)",
+  refiner: "gpt-5.5(xhigh)",
</file context>

constraintCritic: "gpt-5.5(xhigh)",
refiner: "gpt-5.5(xhigh)",
solver: "gpt-5.5(xhigh)",
objectiveLlm: "gpt-5.5(xhigh)",
} as const;

export type AgentRole = keyof typeof DEFAULT_MODELS;
Loading